Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5dd5f32bca0e54b3d6b2488a1d2990355ccec6394221f57286eb29962e6b28
+size 403743472

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c18d224d251724baceba47f4c9e0264e8363cfb1456c8d4c36021814cfdbbf6
+size 807593210

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c1778cf46eda3c47a1a4bcd13d4733549d34a820b6e547f52866d2d517de22
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c88ec23124dbac0116db8fedb3d816b16d2a5a5cd8e9dd18b8cb1a32f34495
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,220 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 42500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 6.019460201263428,
+      "learning_rate": 1.9890916083711463e-05,
+      "loss": 5.6802,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 6.810026168823242,
+      "learning_rate": 1.956604419500441e-05,
+      "loss": 4.6806,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 6.1810994148254395,
+      "learning_rate": 1.903278917399589e-05,
+      "loss": 4.2519,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 8.082925796508789,
+      "learning_rate": 1.8302664407887464e-05,
+      "loss": 4.0159,
+      "step": 8000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.9830644130706787,
+      "eval_runtime": 43.0618,
+      "eval_samples_per_second": 21.945,
+      "eval_steps_per_second": 10.984,
+      "step": 8500
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 8.127954483032227,
+      "learning_rate": 1.7391582974447918e-05,
+      "loss": 3.8114,
+      "step": 10000
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 7.067851543426514,
+      "learning_rate": 1.6319401904115078e-05,
+      "loss": 3.6809,
+      "step": 12000
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 5.324134349822998,
+      "learning_rate": 1.5109489395786475e-05,
+      "loss": 3.543,
+      "step": 14000
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 7.896311283111572,
+      "learning_rate": 1.3788215506652589e-05,
+      "loss": 3.4469,
+      "step": 16000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.529372215270996,
+      "eval_runtime": 42.9645,
+      "eval_samples_per_second": 21.995,
+      "eval_steps_per_second": 11.009,
+      "step": 17000
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 6.048886299133301,
+      "learning_rate": 1.2383659531824114e-05,
+      "loss": 3.3359,
+      "step": 18000
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 11.071381568908691,
+      "learning_rate": 1.0927835785755585e-05,
+      "loss": 3.2524,
+      "step": 20000
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 6.23878288269043,
+      "learning_rate": 9.452527936105895e-06,
+      "loss": 3.1945,
+      "step": 22000
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 10.52528190612793,
+      "learning_rate": 7.987692156775495e-06,
+      "loss": 3.1826,
+      "step": 24000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.3124592304229736,
+      "eval_runtime": 42.9758,
+      "eval_samples_per_second": 21.989,
+      "eval_steps_per_second": 11.006,
+      "step": 25500
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 8.30835247039795,
+      "learning_rate": 6.5674527384518596e-06,
+      "loss": 3.13,
+      "step": 26000
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 9.941985130310059,
+      "learning_rate": 5.222025727614697e-06,
+      "loss": 3.0309,
+      "step": 28000
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 9.763885498046875,
+      "learning_rate": 3.980144450189792e-06,
+      "loss": 2.9941,
+      "step": 30000
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 6.858188629150391,
+      "learning_rate": 2.870115344968626e-06,
+      "loss": 2.9857,
+      "step": 32000
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.428621292114258,
+      "learning_rate": 1.9150471164958117e-06,
+      "loss": 2.9872,
+      "step": 34000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.2195053100585938,
+      "eval_runtime": 43.0622,
+      "eval_samples_per_second": 21.945,
+      "eval_steps_per_second": 10.984,
+      "step": 34000
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 8.133091926574707,
+      "learning_rate": 1.1370511328570388e-06,
+      "loss": 2.9005,
+      "step": 36000
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 7.232800483703613,
+      "learning_rate": 5.51546055042601e-07,
+      "loss": 2.8886,
+      "step": 38000
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 7.69180965423584,
+      "learning_rate": 1.7231245512348337e-07,
+      "loss": 2.9014,
+      "step": 40000
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 11.764738082885742,
+      "learning_rate": 7.273419542405124e-09,
+      "loss": 2.9304,
+      "step": 42000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.2059476375579834,
+      "eval_runtime": 42.8633,
+      "eval_samples_per_second": 22.047,
+      "eval_steps_per_second": 11.035,
+      "step": 42500
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 42500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.876713325662208e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecfced86d830c7997088d0424b02779affdb72497261d1eb2c836f03fab641e
+size 5176